Journal Article

Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning

Ho, Chi-Sing, Dionne, Jennifer, Ermon, Stefano, Holodniy, Mark, Jean, Neal, Saleh, Amr A. E., Blackmon, Lena, Hogan, Catherine A., Banaei, Niaz, Jeffrey, Stefanie S.

2019

Overview

Raman optical spectroscopy promises label-free bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and accuracies remains challenging due to weak Raman signal from bacterial cells and numerous bacterial species and phenotypes. Here we generate an extensive dataset of bacterial Raman spectra and apply deep learning approaches to accurately identify 30 common bacterial pathogens. Even on low signal-to-noise spectra, we achieve average isolate-level accuracies exceeding 82% and antibiotic treatment identification accuracies of 97.0±0.3%. We also show that this approach distinguishes between methicillin-resistant and -susceptible isolates of Staphylococcus aureus (MRSA and MSSA) with 89±0.1% accuracy. We validate our results on clinical isolates from 50 patients. Using just 10 bacterial spectra from each patient isolate, we achieve treatment identification accuracies of 99.7%. Our approach has potential for culture-free pathogen identification and antibiotic susceptibility testing, and could be readily extended for diagnostics on blood, urine, and sputum. The use of Raman spectroscopy for pathogen identification is hampered by the weak Raman signal and phenotypic diversity of bacterial cells. Here the authors generate an extensive dataset of bacterial Raman spectra and apply deep learning to identify common bacterial pathogens and predict antibiotic treatment from noisy Raman spectra.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 631/114/1305 / 631/326/107 / 631/326/421 / 639/624/1107/527/1821 / Anti-Bacterial Agents - therapeutic use / Antibiotics / Bacteria / Bacteria - chemistry / Bacteria - classification / Bacterial Infections - diagnosis / Bacterial Infections - drug therapy / Bacterial Infections - microbiology / Bacterial Typing Techniques / Candida - chemistry / Candida - classification / Cell culture / Clinical isolates / Deep Learning / Drug resistance / Enterococcus - chemistry / Enterococcus - classification / Escherichia coli - chemistry / Escherichia coli - classification / Humanities and Social Sciences / Humans / Identification / Klebsiella - chemistry / Klebsiella - classification / Logistic Models / Machine learning / Methicillin / Methicillin-Resistant Staphylococcus aureus - chemistry / Methicillin-Resistant Staphylococcus aureus - classification / Microbial Sensitivity Tests / multidisciplinary / Neural Networks, Computer / Noise spectra / Pathogens / Patients / Phenotypes / Principal Component Analysis / Proteus mirabilis - chemistry / Proteus mirabilis - classification / Pseudomonas aeruginosa - chemistry / Pseudomonas aeruginosa - classification / Raman spectra / Raman spectroscopy / Salmonella enterica - chemistry / Salmonella enterica - classification / Science / Science (multidisciplinary) / Single-Cell Analysis / Spectroscopy / Spectrum analysis / Spectrum Analysis, Raman - methods / Sputum / Staphylococcus aureus / Staphylococcus aureus - chemistry / Staphylococcus aureus - classification / Streptococcus - chemistry / Streptococcus - classification / Support Vector Machine / Urine